Can NoClick run cited web research automatically with Parallel?

Yes. The Parallel node creates task runs and groups them into task groups, adds runs to an existing group, and retrieves output with Get Task Group Run and Fetch Task Group Runs. Wire these to any trigger so a form submission, a schedule, or an inbound message launches structured research without anyone kicking it off by hand.

How do I connect Parallel to NoClick?

Add your Parallel API key in the node's credentials. Once the key is saved, every operation, from Create Task Run to Create Monitor, runs against your Parallel account, and you can reuse the same credential across multiple workflows.

Can a workflow react when a Parallel monitor detects a change?

Yes. Create a monitor with the node, then use the Receive Webhook Events trigger to start a workflow the moment Parallel sends an event. You can also read a monitor's current state with Get Monitor or stop it with Cancel Monitor from inside the same flow.

What can the node do with FindAll?

FindAll builds and enriches lists of entities that match your criteria. The node can Generate FindAll Spec, Create FindAll Run, Add FindAll Enrichment, Extend FindAll Run to widen results, check progress with Get FindAll Run Status, read output with Get FindAll Run Result, and Cancel FindAll Run if you no longer need it.

Does the node support OpenAI-style chat requests?

Yes. The Chat Completions operation calls Parallel's OpenAI-compatible endpoint, so you can send messages and get research-backed answers in the same shape you would expect from a standard chat API. That makes it easy to slot into steps that already speak the chat completions format.

What does it mean to connect an app to Claude Code?

You wire an integration node into the agent's tools handle. Each operation that app exposes becomes a tool Claude Code can call directly, so it can take real actions in that app instead of only describing them.

Do I need to write any code to set this up?

No. You pick the integrations, click to open the agent in NoClick, connect your accounts, and the tools are ready. There is no glue code to maintain.

Does Claude Code run on my own machine?

No. NoClick runs the harness for you in a hosted sandbox, so there is nothing to install and the agent can run on a schedule or from a trigger.

Can Claude Code use more than one app in a single run?

Yes. Wire as many integrations into the same agent as you need and it can use all of them together while completing a task.

Claude Code

Connect Claude Code to Parallel

Give an AI agent Parallel as a tool and it can go do real web research on its own instead of guessing from memory. It can kick off task runs and task groups, launch FindAll runs to build and enrich entity lists, run fast entity searches, extract page content, and poll the status and results of anything it started, calling each operation as a tool while it works. That lets an autonomous agent gather cited, structured findings mid-task and use them right away rather than stopping to ask.

Loading preview…

Opens a workflow with 30 tools ready to use.

What happens next

Set up in minutes

The open button drops you into a guided setup. It asks exactly this, nothing else:

Choose where it runs
On your computer through your own Claude Code, or hosted in the cloud. The rest of setup adapts to your choice:
Pick what it can do in Parallel
A preset of real Parallel operations. Each one becomes a tool the agent can call, and it can't touch anything outside the list.
Connect Parallel
One sign-in. The agent acts through your account, scoped to the operations you picked.
Add your personal MCP link
The last step mints a private MCP URL for this agent and walks you through exactly this, with your real link filled in. The page flips to Connected the moment your Claude Code first calls in. Claude Code connects when a session starts — run claude, or restart a running one.
Run this in your terminal
$claude mcp add --transport http noclick https://mcp.noclick.app/s/<your-link>
<your-link> is your personal server URL — setup mints it for you.

Exact capabilities

Tools Claude Code gets

Pick the operations you want and each becomes a tool the agent can call directly while it works.

Parallel

30 tools

Search the Web

Run a one-shot web search returning ranked URLs with LLM excerpts.

Extract Page Content

Extract clean markdown excerpts from a list of URLs.

Create Task Run

Start a deep-research / enrichment task run.

Get Task Run

Retrieve a task run object and its status.

Get Task Run Result

Retrieve a completed task run result (blocks until the run finishes or timeout expires).

Get Task Run Input

Retrieve the original input submitted for a task run.

Stream Task Run Events

Stream real-time progress events for an individual task run via SSE.

Create Task Group

Create a batch group to run many task runs together.

Add Runs to Task Group

Add one or more task runs to an existing group.

Fetch Task Group Runs

List runs in a task group.

Stream Task Group Events

Stream real-time events for a task group while runs are active (SSE).

Get Task Group

Retrieve a task group's status and aggregate progress.

Get Task Group Run

Retrieve a single run within a task group.

Create FindAll Run

Discover verified entities matching plain-language criteria.

Generate FindAll Spec

Transform a natural-language objective into a structured FindAll spec (suggested starting point).

Get FindAll Run Status

Poll a FindAll run's status.

Get FindAll Run Result

Get discovered entities / candidates for a FindAll run.

Add FindAll Enrichment

Add column enrichments to a FindAll run's discovered entities.

Extend FindAll Run

Find more entities beyond the original match limit.

Cancel FindAll Run

Cancel an in-progress FindAll run.

Fast Entity Search

Synchronous real-time people / company lookup.

Create Monitor

Set up continuous web tracking.

List Monitors

List monitors (cursor pagination).

Get Monitor

Retrieve a single monitor.

Update Monitor

Update a monitor's config.

List Monitor Events

List detected change events for a monitor.

Trigger Monitor Run

Manually trigger a monitor check now.

Cancel Monitor

Stop / cancel a monitor.

Simulate Monitor Event

Simulate a monitor event to test webhook delivery without waiting for a real run.

Chat Completions

OpenAI-compatible chat completion backed by Parallel web research (Beta).

Starting points

What you can build

When a Parallel monitor fires a webhook, start a workflow that fetches the new finding and posts it to your team channel.

Kick off a FindAll run to build a list of companies matching your ICP, add an enrichment step, then read the results once the run status reports complete.

Batch a set of research questions into a task group, add runs to it, and fetch every run once the group finishes so an AI step can compile one report.

Run a fast entity search on each inbound lead and enrich the record before it lands in your CRM.

Create a monitor to watch a competitor's pricing or news page, and let its webhook trigger an alert whenever the content changes.

Extract clean content from a submitted URL, then pass it to an AI step to summarize or classify before storing it.

Meet the runner

About Claude Code

Claude Code is Anthropic's command-line coding agent. In NoClick you run it as a hosted agent and connect your real apps to its tools handle, so it does far more than write code. Wire in an integration and Claude Code can read and act on Slack, Linear, your database, and more on its own, calling each one as a tool while it works. It is the same capable agent, pointed at your actual workflows instead of a sandbox.

Careful multi-step planning before it acts

Reliable on long, structured tasks

Reads context thoroughly before making changes

Comfortable across code, data, and APIs

Good to know